My environment is odroid-xu3 that constructed with exynos5422 Cortex-A15 2.0Ghz quad core and Cortex-A7 quad core CPUs and have Ubuntu 18.04, Linux kernel 4.14.141-69.
My issue is that I am running AlexNet example from the compute library and setting the cores to the big A15 cores using taskset and threads=4, but the execution time of the inference, which I measure using the time command is coming out to be around :
real 0m11.211suser 0m9.086ssys 0m2.041s
Isnt't this too high? I have read papers and they have reported inference time in the order of mili seconds. What can be the issue?
I built the library using assert=0 and debug =0 NEON =1 OPENCL=1
and the command I am using to run the example is
taskset -c 4,5,6,7 ./build/examples/graph_alexnet --data=$PATH_ASSETS --image=$PATH_ASSETS/go_kart.ppm --labels=$PATH_ASSETS/labels.txt
Please post your questions to GitHub forum, where our Compute Library engineering team is taking care of that. Thus you can get more prompt response on your questions. Thanks.
View all questions in Machine Learning forum